Results 1  10
of
2,033
The Asymptotic ConvergenceRate of Qlearning
, 1998
"... In this paper we show that for discounted MDPs with discount factor fl ? 1=2 the asymptotic rate of convergence of Qlearning is O(1=t R(1\Gammafl) ) if R(1 \Gamma fl) ! 1=2 and O( p log log t=t) otherwise provided that the stateaction pairs are sampled from a fixed probability distribution. He ..."
Abstract

Cited by 22 (3 self)
 Add to MetaCart
In this paper we show that for discounted MDPs with discount factor fl ? 1=2 the asymptotic rate of convergence of Qlearning is O(1=t R(1\Gammafl) ) if R(1 \Gamma fl) ! 1=2 and O( p log log t=t) otherwise provided that the stateaction pairs are sampled from a fixed probability distribution
The Asymptotic ConvergenceRate of QIearning
"... szepes((trnath.uszeged.hu In this paper we show that for discounted MDPs with discount factor ' (> 1/2 the asymptotic rate of convergence of Qlearning is O(I/tR(lO)) if R(1 ':I) < 1/2 and O ( Jlog log t/t) otherwise provided that the stateaction pairs are sampled from a fixed pr ..."
Abstract
 Add to MetaCart
szepes((trnath.uszeged.hu In this paper we show that for discounted MDPs with discount factor ' (> 1/2 the asymptotic rate of convergence of Qlearning is O(I/tR(lO)) if R(1 ':I) < 1/2 and O ( Jlog log t/t) otherwise provided that the stateaction pairs are sampled from a fixed
Asymptotic Convergence Rate of the EM Algorithm for Gaussian Mixtures
, 2000
"... ... This article studies this problem asymptotically in the setting of gaussian mixtures under the theoretical framework of Xu and Jordan (1996). It has been proved that the asymptotic convergence rate of the EM algorithm for gaussian mixtures locally around the true solution 2 is o.e 0:5" . ..."
Abstract

Cited by 25 (2 self)
 Add to MetaCart
... This article studies this problem asymptotically in the setting of gaussian mixtures under the theoretical framework of Xu and Jordan (1996). It has been proved that the asymptotic convergence rate of the EM algorithm for gaussian mixtures locally around the true solution 2 is o.e 0:5"
The asymptotic convergence rates of Fourier path integral methods
"... The asymptotic rates of convergence of thermodynamic properties with respect to the number of Fourier coefficients, k max , included in Fourier path integral calculations are derived. The convergence rates are developed both with and without partial averaging for operators diagonal in coordinate rep ..."
Abstract
 Add to MetaCart
The asymptotic rates of convergence of thermodynamic properties with respect to the number of Fourier coefficients, k max , included in Fourier path integral calculations are derived. The convergence rates are developed both with and without partial averaging for operators diagonal in coordinate
LETTER Communicated by Chris Williams Asymptotic Convergence Rate of the EM Algorithm for Gaussian Mixtures
"... It is well known that the convergence rate of the expectationmaximization (EM) algorithm can be faster than those of convention firstorder iterative algorithms when the overlap in the given mixture is small. But this argument has not been mathematically proved yet. This article studies this probl ..."
Abstract
 Add to MetaCart
this problem asymptotically in the setting of gaussian mixtures under the theoretical framework of Xu and Jordan (1996). It has been proved that the asymptotic convergence rate of the EM algorithm for gaussian mixtures locally around the true solution2 ⁄ is o.e0:5¡".2⁄//, where "> 0 is an arbi
c ⃝ World Scientific Publishing Company
, 2015
"... DOI: 10.1142/S0218202515500426 Timeasymptotic convergence rates towards the discrete evolutionary stable distribution ..."
Abstract
 Add to MetaCart
DOI: 10.1142/S0218202515500426 Timeasymptotic convergence rates towards the discrete evolutionary stable distribution
Asymptotic accuracy of Iterative Feedback Tuning
, 2004
"... Iterative Feedback Tuning (IFT) is a widely used procedure for controller tuning. It is a sequence of iteratively performed special experiments on the plant interlaced with periods of data collection under normal operating conditions. In this paper we derive the asymptotic convergence rate of IFT fo ..."
Abstract

Cited by 5 (3 self)
 Add to MetaCart
Iterative Feedback Tuning (IFT) is a widely used procedure for controller tuning. It is a sequence of iteratively performed special experiments on the plant interlaced with periods of data collection under normal operating conditions. In this paper we derive the asymptotic convergence rate of IFT
Convergence analysis of a PageRank updating algorithm by Langville and Meyer
 SIAM J. Matrix Anal. Appl
"... Abstract. The PageRank updating algorithm proposed by Langville and Meyer is a special case of an iterative aggregation/disaggregation (SIAD) method for computing stationary distributions of very large Markov chains. It is designed, in particular, to speed up the determination of PageRank, which is ..."
Abstract

Cited by 18 (2 self)
 Add to MetaCart
convergence rate of the SIAD method. It is known that the power method applied to the Google matrix always converges, and we show that the asymptotic convergence rate of the SIAD method is at least as good as that of the power method. Furthermore, by exploiting the hyperlink structure of the web it can
Design of capacityapproaching irregular lowdensity paritycheck codes
 IEEE TRANS. INFORM. THEORY
, 2001
"... We design lowdensity paritycheck (LDPC) codes that perform at rates extremely close to the Shannon capacity. The codes are built from highly irregular bipartite graphs with carefully chosen degree patterns on both sides. Our theoretical analysis of the codes is based on [1]. Assuming that the unde ..."
Abstract

Cited by 588 (6 self)
 Add to MetaCart
We design lowdensity paritycheck (LDPC) codes that perform at rates extremely close to the Shannon capacity. The codes are built from highly irregular bipartite graphs with carefully chosen degree patterns on both sides. Our theoretical analysis of the codes is based on [1]. Assuming
SpaceAlternating Generalized ExpectationMaximization Algorithm
 IEEE Trans. Signal Processing
, 1994
"... The expectationmaximization (EM) method can facilitate maximizing likelihood functions that arise in statistical estimation problems. In the classical EM paradigm, one iteratively maximizes the conditional loglikelihood of a single unobservable complete data space, rather than maximizing the intra ..."
Abstract

Cited by 193 (28 self)
 Add to MetaCart
EM (SAGE) method, which updates the parameters sequentially by alternating between several small hiddendata spaces defined by the algorithm designer. We prove that the sequence of estimates monotonically increases the penalizedlikelihood objective, we derive asymptotic convergence rates, and we
Results 1  10
of
2,033